• Journal of Korea Water Resources Association
• /
• v.50 no.10
• /
• pp.681-690
• /
• 2017

This study estimated the daily maximum snow depth using the Artificial Neural Network (ANN) model in Korean Peninsula. First, the optimal ANN model structure was determined through the trial-and-error approach. As a result, daily precipitation, daily mean temperature, and daily minimum temperature were chosen as the input data of the ANN. The number of hidden layer was set to 1 and the number of nodes in the hidden layer was set to 10. In case of using the observed value as the input data of the ANN model, the cross validation correlation coefficient was 0.87, which is higher than that of the case in which the daily maximum snow depth was spatially interpolated using the Ordinary Kriging method (0.40). In order to investigate the performance of the ANN model for estimating the daily maximum snow depth of the ungauged area, the input data of the ANN model was spatially interpolated using Ordinary Kriging. In this case, the correlation coefficient of 0.49 was obtained. The performance of the ANN model in mountainous areas above 200m above sea level was found to be somewhat lower than that in the rest of the study area. This result of this study implies that the ANN model can be used effectively for the accurate and immediate estimation of the maximum snow depth over the whole country.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.3
• /
• pp.1724-1733
• /
• 2014

This paper presents a pattern recognition analysis of two spirals problem and optimization of Cascade Correlation learning algorithm using in combination with a non-monotone function as CosExp(cosine-modulated symmetric exponential function) and a monotone function as sigmoid function. In addition, the algorithm's optimization is attempted. By using genetic algorithms the optimization of the algorithm will attempt. In the first experiment, by using CosExp activation function for candidate neurons of the learning algorithm is analyzed the recognized pattern in input space of the two spirals problem. In the second experiment, CosExp function for output neurons is used. In the third experiment, the sigmoid activation functions with various parameters for candidate neurons in 8 pools and CosExp function for output neurons are used. In the fourth experiment, the parameters are composed of 8 pools and displacement of the sigmoid function to determine the value of the three parameters is obtained using genetic algorithms. The parameter values applied to the sigmoid activation functions for candidate neurons are used. To evaluate the performance of these algorithms, each step of the training input pattern classification shows the shape of the two spirals. In the optimizing process, the number of hidden neurons was reduced from 28 to15, and finally the learning algorithm with 12 hidden neurons was optimized.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.3
• /
• pp.414-419
• /
• 2020

An artificial intelligence-based cable tension estimation model was developed to expand the utilization of data obtained from cable accelerometers of cable-stayed bridges. The model was based on an algorithm for selecting the natural frequency in the tension estimation process based on the vibration method and an applied artificial neural network (ANN). The training data of the ANN was composed after converting the cable acceleration data into the frequency, and machine learning was carried out using the characteristics with a pattern on the natural frequency. When developing the training data, the frequencies with various amplitudes can be used to represent the frequencies of multiple shapes to improve the selection performance for natural frequencies. The performance of the model was estimated by comparing it with the control criteria of the tension estimated by an expert. As a result of the verification using 139 frequencies obtained from the cable accelerometer as the input, the natural frequency was determined to be similar to the real criteria and the estimated tension of the cable by the natural frequency was 96.4% of the criteria.

• Journal of the Korean Society of Radiology
• /
• v.3 no.1
• /
• pp.29-39
• /
• 2009

In this paper has proposed to the recognition of the disease on medical images using neural network. The neural network is constructed as three-layers of the input-layer, the hidden-layer and the output-layer. The training method applied for the recognition of disease region is adaptive error back-propagation. The low-frequency region analyzed by DWT are expressed by matrix. The coefficient-values of the characteristic polynomial applied are n+1. The normalized maximum value +1 and minimum value -1 in the range of tangent-sigmoid transfer function are applied to be use as the input vector of the neural network. To prove the validity of the proposed methods used in the experiment with a simulation experiment, the input medical image recognition rate the evaluation of areas of disease. As a result of the experiment, the characteristic polynomial coefficient of low-frequency area matrix, conversed to 4 level DWT, was proved to be optimum to be applied to the feature parameter. As for the number of training, it was marked fewest in 0.01 of learning coefficient and 0.95 of momentum, when the adaptive error back-propagation was learned by inputting standardized feature parameter into organized neural network. As to the training result when the learning coefficient was 0.01, and momentum was 0.95, it was 100% recognized in fifty-five times of the stomach image, fifty-five times of the chest image, forty-six times of the CT image, fifty-five times of ultrasonogram, and one hundred fifty-seven times of angiogram.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.33 no.2
• /
• pp.84-91
• /
• 2005

For long time, the takeoff and landing control of airship was worked by human handling. With the development of the autonomous control system, the exact controls during the takeoff and landing were required and lots of methods and algorithms were suggested. This paper presents the result of airship take-off and landing by buoyancy control using air ballonet volume change and performance control of pitch angle for stable flight within the desired altitude. For the complexity of airship's dynamics, firstly, simple PID controller was applied. Due to the various atmospheric conditions, this controller didn't give satisfactory results. Therefore, new control method was designed to reduce rapidly the error between designed trajectory and actual trajectory by learning algorithm using an artificial neural network. Generally, ANN has various weaknesses such as large training time, selection of neuron and hidden layer numbers required to deal with complex problem. To overcome these drawbacks, in this paper, the RBFN (radial basis function network) controller developed. The weight value of RBFN is acquired by learning which to reduce the error between desired input output through and airship dynamics to impress the disturbance. As a result of simulation, the controller using the RBFN is superior to PID controller which maximum error is 15M.

• The Journal of Engineering Geology
• /
• v.15 no.1
• /
• pp.67-76
• /
• 2005

This paper presents the application of a neural network for prediction of the unconfined compressive strength from physical properties and schmidt hardness number on rock samples. To investigate the suitability of this approach, the results of analysis using a neural network are compared to predictions obtained by statistical relations. The data sets containing 55 rock sample records which are composed of sandstone and shale were assembled in Daegu area. They were used to learn the neural network model with the back-propagation teaming algorithm. The rock characteristics as the teaming input of the neural network are: schmidt hardness number, specific gravity, absorption, porosity, p-wave velocity and S-wave velocity, while the corresponding unconfined compressive strength value functions as the teaming output of the neural network. A data set containing 45 test results was used to train the networks with the back-propagation teaming algorithm. Another data set of 10 test results was used to validate the generalization and prediction capabilities of the neural network.

• Journal of Internet Computing and Services
• /
• v.16 no.2
• /
• pp.67-75
• /
• 2015

According to the changes of the mobile environments, the usage and interest of the Android apps have been increased. But the usage of illegally-copied apps has been also increased. And the transparency and dependability of the app markets has been decreased. Therefore there are many cases for the copyright infringement of app developers. Although several methods for preventing illegally-copied apps have been studied, there may exist possible ways to bypass the methods. Since it is difficult to find out the first distributors of the illegally-copied apps, it is not easy to punish them legally. This paper proposes the method of detecting illegally-copied apps. The proposed detector can detect the illegally-copied apps using odex file, which is created when the app is installed. The detector can also find out the information of the first distributors based on forensic watermark technique. Since the illegally-copied app detector is running as a service on the system server, it is granted that the detector hides from the users. As an experiment result, the illegally-copied app detector takes on average within 0.2 seconds to detect and delete an illegally-copied app.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.9
• /
• pp.75-84
• /
• 2012

HMM-based Text-to-Speech systems generally utilize context dependent tri-phone units from a large corpus speech DB to enhance the synthetic speech. To downsize a large corpus speech DB, acoustically similar tri-phone units are clustered based on the decision tree using context dependent information. Context dependent information includes phoneme sequence as well as prosodic information because the naturalness of synthetic speech highly depends on the prosody such as pause, intonation pattern, and segmental duration. However, if the prosodic information was complicated, many context dependent phonemes would have no examples in the training data, and clustering would provide a smoothed feature which will generate unnatural synthetic speech. In this paper, instead of complicate prosodic information we propose a simple three prosodic boundary types and decision tree questions that use rising tone, falling tone, and monotonic tone to improve naturalness. Experimental results show that our proposed method can improve naturalness of a HMM-based Korean TTS and get high MOS in the perception test.

• Journal of Biomedical Engineering Research
• /
• v.18 no.4
• /
• pp.429-438
• /
• 1997

Mechanical valve is one of the most widely used implantable artificial organs of which the reliability is so important that its failure means the death of patient. Therefore early noninvasive detection is essentially required, though mechanical valve failure with thrombosis is the most common. The objective of this paper is to detect the thrombosis formation by spectral analysis and neural network. Using microphone and amplifier, we measured the sound from the mechanical valve which is attached to the pneumatic ventricular assist device. The sound was sampled by A/D converter(DaqBook 100) and the periodogram is the main algorithm for obtaining spectrum. We made the thrombosis models using pellethane and silicon and they are thrombosis model on the valvular disk, around the sewing ring and fibrous tissue growth across the orifice of valve. The performance of the measurment system was tested firstly using 1 KHz sinusoidal wave. The measurement system detected well 1KHz spectrum as expected. The spectrum of normal and 5 kinds of thrombotic valve were obtained and primary and secondary peak appeared in each spectrum waveform. We find that the secondary peak changes according to the thrombosis model. So to distinguish the secondary peak of normal and thrombotic valve quantatively, 3 layer back propagation neural network, which contains 7, 000 input node, 20 hidden layer and 1 output was employed The trained neural network can distinguish normal and valve with more than 90% probability. As a conclusion, the noninvasive monitoring of implanted mechanical valve is possible by analysing the acoustical spectrum using neural network algorithm and this method will be applied to the performance evaluation of other implantable artificial organs.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.6
• /
• pp.100-110
• /
• 2007

When compressed video data is transmitted over error-prone network such as wireless channel, data is likely to be lost, so the quality of reconstructed picture is severely decreased. It is specially so in case that important information such as motion vector or macroblock mode is lost. H.264/AVC standard includes DP as error resilient technique for protecting important information from error in which data is labeled according to its relative importance. But DP technique requires a network that supports different reliabilities of transmitted data. In general, the benefits of UEP is sought by sending multiple times of same packets corresponding to important information. In this paper, we propose MDC technique based on data partitioning technique. The proposed method encodes motion vector of H.264/AVC standard into multiple parts using MDC and transmits each part as independent packet. Even if partial packet is lost, the proposed scheme can decode the compressed bitstream by using estimated motion vector with partial packets correctly transmitted, so that achieving improved performance of error concealment with minimal effect of channel error. Also in decoding process, the proposed multiple description matching increases the accuracy of estimated lost motion vector and quality of reconstructed video.